How Ronja learns

Ronja doesn’t just read your tables — she accumulates understanding of your business over time. That understanding lives on three surfaces, each with its own scope and audience.

Surface	Scope	Best for
Notes	One feature	Procedures and facts about that feature’s data
Knowledge	The whole organization	Org-wide rules, terminology, definitions
Data dictionary	One table	What each table and column means

Notes: teach Ronja within a feature

A note is a document attached to a feature. Notes come in two kinds, shown as two lanes on the feature page:

• Skills teach Ronja a task — a runnable procedure, like “how we build the weekly revenue report”.
• Knowledge notes are reference material about that feature’s data — how a table behaves, how a metric is actually calculated, known caveats.

There is no “New note” button anywhere: you create and edit notes by asking Ronja in an exploration. She writes the note, opens it beside the chat for you to read, and from then on loads it automatically whenever a request touches that topic. On shared features, note edits go through drafts and review like any other shared resource. See Write notes.

Knowledge: what the whole organization knows

The Knowledge page (in the admin sidebar) is Ronja’s organization-wide memory: KPI definitions, business rules, terminology, fiscal calendars — anything that should apply in every conversation, in every workspace. Three ideas define it:

• Ronja learns much of it herself. Entries are marked “Created by AI” or “Created by user”.
• Tell, don’t edit. Knowledge has no edit button. Admins correct it by clicking Curate in chat and telling Ronja what’s wrong (“our fiscal year starts in April, not January”); Ronja decides where the correction belongs and keeps everything organized.
• It’s always on. The organization’s core context is injected into every session automatically; deeper entries load on demand.

Organization Knowledge: browse the tree, and curate by chatting — never by editing.

Everyone can browse Knowledge read-only (the page sits in the admin sidebar, so non-admins need a direct link); curating is admin-only. See Curate Knowledge.

The data dictionary: what your data means

The data dictionary is the per-table layer: the descriptions and metadata that tell Ronja what a table and its columns actually represent. Its Catalog view lists per-column statistics — Field, Kind, Rows, Missing, Cardinality, Examples. Good descriptions here change answer quality directly, because they’re what Ronja consults when deciding which data answers a question. See Maintain the data dictionary.

Choosing the right surface

• “Always report money in SEK” → Knowledge — an org-wide rule that applies everywhere.
• “Active revenue is net of refunds, computed from these columns” → a knowledge note in that feature.
• “I personally prefer tables over charts” → your Personal memory, a short editable note about yourself under Account → Memory — the one piece of Ronja’s memory you edit directly.

For the Note-vs-Knowledge distinction in one place, see What’s the difference?.